linux-stable/tools/perf/Documentation/perf-annotate.txt

158 lines
4 KiB
Text
Raw Normal View History

perf-annotate(1)
================
NAME
----
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 13:48:52 +00:00
perf-annotate - Read perf.data (created by perf record) and display annotated code
SYNOPSIS
--------
[verse]
'perf annotate' [-i <file> | --input=file] [symbol_name]
DESCRIPTION
-----------
perf_counter tools: Add 'perf annotate' feature Add new perf sub-command to display annotated source code: $ perf annotate decode_tree_entry ------------------------------------------------ Percent | Source code & Disassembly of /home/mingo/git/git ------------------------------------------------ : : /home/mingo/git/git: file format elf64-x86-64 : : : Disassembly of section .text: : : 00000000004a0da0 <decode_tree_entry>: : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 3.82 : 4a0da0: 41 54 push %r12 : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx : *modep = mode; : return str; : } : : static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size) : { 0.00 : 4a0da6: 49 89 fc mov %rdi,%r12 0.00 : 4a0da9: 55 push %rbp 3.37 : 4a0daa: 53 push %rbx : const char *path; : unsigned int mode, len; : : if (size < 24 || buf[size - 21]) 0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1) 3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80> : static const char *get_mode(const char *str, unsigned int *modep) : { : unsigned char c; : unsigned int mode = 0; : : if (*str == ' ') 1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax 0.39 : 4a0db7: 3c 20 cmp $0x20,%al 0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80> : return NULL; : : while ((c = *str++) != ' ') { 0.06 : 4a0dbb: 89 c2 mov %eax,%edx : if (c < '0' || c > '7') 1.99 : 4a0dbd: 31 ed xor %ebp,%ebp : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx : if (c < '0' || c > '7') 0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax 0.17 : 4a0dc6: 3c 07 cmp $0x7,%al 0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37> 0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80> 0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax) 16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax 0.14 : 4a0dd3: 3c 07 cmp $0x7,%al 0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80> : return NULL; : mode = (mode << 3) + (c - '0'); 3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax : unsigned int mode = 0; : : if (*str == ' ') : return NULL; : : while ((c = *str++) != ' ') { 0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx 16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx : if (c < '0' || c > '7') : return NULL; : mode = (mode << 3) + (c - '0'); The first column is the percentage of samples that arrived on that particular line - relative to the total cost of the function. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 13:48:52 +00:00
This command reads the input file and displays an annotated version of the
code. If the object file has debug symbols then the source code will be
displayed alongside assembly code.
If there is no debug info in the object, then annotated assembly is displayed.
OPTIONS
-------
-i::
--input=<file>::
Input file name. (default: perf.data unless stdin is a fifo)
-d::
--dsos=<dso[,dso...]>::
Only consider symbols in these dsos.
-s::
--symbol=<symbol>::
Symbol to annotate.
-f::
--force::
Don't do ownership validation.
-v::
--verbose::
Be more verbose. (Show symbol address, etc)
-q::
--quiet::
Do not show any warnings or messages. (Suppress -v)
-n::
--show-nr-samples::
Show the number of samples for each symbol
-D::
--dump-raw-trace::
Dump raw trace in ASCII.
-k::
--vmlinux=<file>::
vmlinux pathname.
perf annotate: Introduce --ignore-vmlinux command line option This is already present in 'perf top', albeit undocumented (will fix), and is useful to use /proc/kcore instead of vmlinux and then get what is really in place, not what the kernel starts with, before alternatives, ftrace .text patching, etc, see the differences: # perf annotate --stdio2 _raw_spin_lock_irqsave _raw_spin_lock_irqsave() /lib/modules/4.16.0-rc4/build/vmlinux Event: anon group { cycles, instructions } 0.00 3.17 → callq __fentry__ 0.00 7.94 push %rbx 7.69 36.51 → callq __page_file_index mov %rax,%rbx 7.69 3.17 → callq *ffffffff82225cd0 xor %eax,%eax mov $0x1,%edx 80.77 49.21 lock cmpxchg %edx,(%rdi) test %eax,%eax ↓ jne 2b 3.85 0.00 mov %rbx,%rax pop %rbx ← retq 2b: mov %eax,%esi → callq queued_spin_lock_slowpath mov %rbx,%rax pop %rbx ← retq [root@jouet ~]# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave _raw_spin_lock_irqsave() /proc/kcore Event: anon group { cycles, instructions } 0.00 3.17 nop 0.00 7.94 push %rbx 0.00 23.81 pushfq 7.69 12.70 pop %rax nop mov %rax,%rbx 7.69 3.17 cli nop xor %eax,%eax mov $0x1,%edx 80.77 49.21 lock cmpxchg %edx,(%rdi) test %eax,%eax ↓ jne 2b 3.85 0.00 mov %rbx,%rax pop %rbx ← retq 2b: mov %eax,%esi → callq *ffffffff820e96b0 mov %rbx,%rax pop %rbx ← retq # Diff of the output of those commands: # perf annotate --stdio2 _raw_spin_lock_irqsave > /tmp/vmlinux # perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave > /tmp/kcore # diff -y /tmp/vmlinux /tmp/kcore _raw_spin_lock_irqsave() vmlinux | _raw_spin_lock_irqsave() /proc/kcore Event: anon group { cycles, instructions } Event: anon group { cycles, instructions } 0.00 3.17 → callq __fentry__ | 0.00 3.17 nop 0.00 7.94 push %rbx 0.00 7.94 push %rbx 7.69 36.51 → callq __page_file_index | 0.00 23.81 pushfq > 7.69 12.70 pop %rax > nop mov %rax,%rbx mov %rax,%rbx 7.69 3.17 → callq *ffffffff82225cd0 | 7.69 3.17 cli > nop xor %eax,%eax xor %eax,%eax mov $0x1,%edx mov $0x1,%edx 80.77 49.21 lock cmpxchg %edx,(%rdi) 80.77 49.21 lock cmpxchg %edx,(%rdi) test %eax,%eax test %eax,%eax ↓ jne 2b ↓ jne 2b 3.85 0.00 mov %rbx,%rax 3.85 0.00 mov %rbx,%rax pop %rbx pop %rbx ← retq ← retq 2b: mov %eax,%esi 2b: mov %eax,%esi → callq queued_spin_lock_slowpath| → callq *ffffffff820e96b0 mov %rbx,%rax mov %rbx,%rax pop %rbx pop %rbx ← retq ← retq # This should be further streamlined by doing both annotations and allowing the TUI to toggle initial/current, and show the patched instructions in a slightly different color. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-wz8d269hxkcwaczr0r4rhyjg@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 18:58:35 +00:00
--ignore-vmlinux::
Ignore vmlinux files.
perf annotate: Add itrace options support The "auxtrace_info" and "auxtrace" functions are not set in "tool" member of "annotate". As a result, perf annotate does not support parsing itrace data. Before: # perf record -e arm_spe_0/branch_filter=1/ -a sleep 1 [ perf record: Woken up 9 times to write data ] [ perf record: Captured and wrote 20.874 MB perf.data ] # perf annotate --stdio Error: The perf.data data has no samples! Solution: 1. Add itrace options in help, 2. Set hook functions of "id_index", "auxtrace_info" and "auxtrace" in perf_tool. After: # perf record --all-user -e arm_spe_0/branch_filter=1/ ls Couldn't synthesize bpf events. perf.data [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.010 MB perf.data ] # perf annotate --stdio Percent | Source code & Disassembly of libc-2.28.so for branch-miss (1 samples, percent: local period) ------------------------------------------------------------------------------------------------------------ : : : : Disassembly of section .text: : : 0000000000066180 <__getdelim@@GLIBC_2.17>: 0.00 : 66180: stp x29, x30, [sp, #-96]! 0.00 : 66184: cmp x0, #0x0 0.00 : 66188: ccmp x1, #0x0, #0x4, ne // ne = any 0.00 : 6618c: mov x29, sp 0.00 : 66190: stp x24, x25, [sp, #56] 0.00 : 66194: stp x26, x27, [sp, #72] 0.00 : 66198: str x28, [sp, #88] 0.00 : 6619c: b.eq 66450 <__getdelim@@GLIBC_2.17+0x2d0> // b.none 0.00 : 661a0: stp x22, x23, [x29, #40] 0.00 : 661a4: mov x22, x1 0.00 : 661a8: ldr w1, [x3] 0.00 : 661ac: mov w23, w2 0.00 : 661b0: stp x20, x21, [x29, #24] 0.00 : 661b4: mov x20, x3 0.00 : 661b8: mov x21, x0 0.00 : 661bc: tbnz w1, #15, 66360 <__getdelim@@GLIBC_2.17+0x1e0> 0.00 : 661c0: ldr x0, [x3, #136] 0.00 : 661c4: ldr x2, [x0, #8] 0.00 : 661c8: str x19, [x29, #16] 0.00 : 661cc: mrs x19, tpidr_el0 0.00 : 661d0: sub x19, x19, #0x700 0.00 : 661d4: cmp x2, x19 0.00 : 661d8: b.eq 663f0 <__getdelim@@GLIBC_2.17+0x270> // b.none 0.00 : 661dc: mov w1, #0x1 // #1 0.00 : 661e0: ldaxr w2, [x0] 0.00 : 661e4: cmp w2, #0x0 0.00 : 661e8: b.ne 661f4 <__getdelim@@GLIBC_2.17+0x74> // b.any 0.00 : 661ec: stxr w3, w1, [x0] 0.00 : 661f0: cbnz w3, 661e0 <__getdelim@@GLIBC_2.17+0x60> 0.00 : 661f4: b.ne 66448 <__getdelim@@GLIBC_2.17+0x2c8> // b.any 0.00 : 661f8: ldr x0, [x20, #136] 0.00 : 661fc: ldr w1, [x20] 0.00 : 66200: ldr w2, [x0, #4] 0.00 : 66204: str x19, [x0, #8] 0.00 : 66208: add w2, w2, #0x1 0.00 : 6620c: str w2, [x0, #4] 0.00 : 66210: tbnz w1, #5, 66388 <__getdelim@@GLIBC_2.17+0x208> 0.00 : 66214: ldr x19, [x29, #16] 0.00 : 66218: ldr x0, [x21] 0.00 : 6621c: cbz x0, 66228 <__getdelim@@GLIBC_2.17+0xa8> 0.00 : 66220: ldr x0, [x22] 0.00 : 66224: cbnz x0, 6623c <__getdelim@@GLIBC_2.17+0xbc> 0.00 : 66228: mov x0, #0x78 // #120 0.00 : 6622c: str x0, [x22] 0.00 : 66230: bl 20710 <malloc@plt> 0.00 : 66234: str x0, [x21] 0.00 : 66238: cbz x0, 66428 <__getdelim@@GLIBC_2.17+0x2a8> 0.00 : 6623c: ldr x27, [x20, #8] 0.00 : 66240: str x19, [x29, #16] 0.00 : 66244: ldr x19, [x20, #16] 0.00 : 66248: sub x19, x19, x27 0.00 : 6624c: cmp x19, #0x0 0.00 : 66250: b.le 66398 <__getdelim@@GLIBC_2.17+0x218> 0.00 : 66254: mov x25, #0x0 // #0 0.00 : 66258: b 662d8 <__getdelim@@GLIBC_2.17+0x158> 0.00 : 6625c: nop 0.00 : 66260: add x24, x19, x25 0.00 : 66264: ldr x3, [x22] 0.00 : 66268: add x26, x24, #0x1 0.00 : 6626c: ldr x0, [x21] 0.00 : 66270: cmp x3, x26 0.00 : 66274: b.cs 6629c <__getdelim@@GLIBC_2.17+0x11c> // b.hs, b.nlast 0.00 : 66278: lsl x3, x3, #1 0.00 : 6627c: cmp x3, x26 0.00 : 66280: csel x26, x3, x26, cs // cs = hs, nlast 0.00 : 66284: mov x1, x26 0.00 : 66288: bl 206f0 <realloc@plt> 0.00 : 6628c: cbz x0, 66438 <__getdelim@@GLIBC_2.17+0x2b8> 0.00 : 66290: str x0, [x21] 0.00 : 66294: ldr x27, [x20, #8] 0.00 : 66298: str x26, [x22] 0.00 : 6629c: mov x2, x19 0.00 : 662a0: mov x1, x27 0.00 : 662a4: add x0, x0, x25 0.00 : 662a8: bl 87390 <explicit_bzero@@GLIBC_2.25+0x50> 0.00 : 662ac: ldr x0, [x20, #8] 0.00 : 662b0: add x19, x0, x19 0.00 : 662b4: str x19, [x20, #8] 0.00 : 662b8: cbnz x28, 66410 <__getdelim@@GLIBC_2.17+0x290> 0.00 : 662bc: mov x0, x20 0.00 : 662c0: bl 73b80 <__underflow@@GLIBC_2.17> 0.00 : 662c4: cmn w0, #0x1 0.00 : 662c8: b.eq 66410 <__getdelim@@GLIBC_2.17+0x290> // b.none 0.00 : 662cc: ldp x27, x19, [x20, #8] 0.00 : 662d0: mov x25, x24 0.00 : 662d4: sub x19, x19, x27 0.00 : 662d8: mov x2, x19 0.00 : 662dc: mov w1, w23 0.00 : 662e0: mov x0, x27 0.00 : 662e4: bl 807b0 <memchr@@GLIBC_2.17> 0.00 : 662e8: cmp x0, #0x0 0.00 : 662ec: mov x28, x0 0.00 : 662f0: sub x0, x0, x27 0.00 : 662f4: csinc x19, x19, x0, eq // eq = none 0.00 : 662f8: mov x0, #0x7fffffffffffffff // #9223372036854775807 0.00 : 662fc: sub x0, x0, x25 0.00 : 66300: cmp x19, x0 0.00 : 66304: b.lt 66260 <__getdelim@@GLIBC_2.17+0xe0> // b.tstop 0.00 : 66308: adrp x0, 17f000 <sys_sigabbrev@@GLIBC_2.17+0x320> 0.00 : 6630c: ldr x0, [x0, #3624] 0.00 : 66310: mrs x2, tpidr_el0 0.00 : 66314: ldr x19, [x29, #16] 0.00 : 66318: mov w3, #0x4b // #75 0.00 : 6631c: ldr w1, [x20] 0.00 : 66320: mov x24, #0xffffffffffffffff // #-1 0.00 : 66324: str w3, [x2, x0] 0.00 : 66328: tbnz w1, #15, 66340 <__getdelim@@GLIBC_2.17+0x1c0> 0.00 : 6632c: ldr x0, [x20, #136] 0.00 : 66330: ldr w1, [x0, #4] 0.00 : 66334: sub w1, w1, #0x1 0.00 : 66338: str w1, [x0, #4] 0.00 : 6633c: cbz w1, 663b8 <__getdelim@@GLIBC_2.17+0x238> 0.00 : 66340: mov x0, x24 0.00 : 66344: ldr x28, [sp, #88] 0.00 : 66348: ldp x20, x21, [x29, #24] 0.00 : 6634c: ldp x22, x23, [x29, #40] 0.00 : 66350: ldp x24, x25, [sp, #56] 0.00 : 66354: ldp x26, x27, [sp, #72] 0.00 : 66358: ldp x29, x30, [sp], #96 0.00 : 6635c: ret 100.00 : 66360: tbz w1, #5, 66218 <__getdelim@@GLIBC_2.17+0x98> 0.00 : 66364: ldp x20, x21, [x29, #24] 0.00 : 66368: mov x24, #0xffffffffffffffff // #-1 0.00 : 6636c: ldp x22, x23, [x29, #40] 0.00 : 66370: mov x0, x24 0.00 : 66374: ldp x24, x25, [sp, #56] 0.00 : 66378: ldp x26, x27, [sp, #72] 0.00 : 6637c: ldr x28, [sp, #88] 0.00 : 66380: ldp x29, x30, [sp], #96 0.00 : 66384: ret 0.00 : 66388: mov x24, #0xffffffffffffffff // #-1 0.00 : 6638c: ldr x19, [x29, #16] 0.00 : 66390: b 66328 <__getdelim@@GLIBC_2.17+0x1a8> 0.00 : 66394: nop 0.00 : 66398: mov x0, x20 0.00 : 6639c: bl 73b80 <__underflow@@GLIBC_2.17> 0.00 : 663a0: cmn w0, #0x1 0.00 : 663a4: b.eq 66438 <__getdelim@@GLIBC_2.17+0x2b8> // b.none 0.00 : 663a8: ldp x27, x19, [x20, #8] 0.00 : 663ac: sub x19, x19, x27 0.00 : 663b0: b 66254 <__getdelim@@GLIBC_2.17+0xd4> 0.00 : 663b4: nop 0.00 : 663b8: str xzr, [x0, #8] 0.00 : 663bc: ldxr w2, [x0] 0.00 : 663c0: stlxr w3, w1, [x0] 0.00 : 663c4: cbnz w3, 663bc <__getdelim@@GLIBC_2.17+0x23c> 0.00 : 663c8: cmp w2, #0x1 0.00 : 663cc: b.le 66340 <__getdelim@@GLIBC_2.17+0x1c0> 0.00 : 663d0: mov x1, #0x81 // #129 0.00 : 663d4: mov x2, #0x1 // #1 0.00 : 663d8: mov x3, #0x0 // #0 0.00 : 663dc: mov x8, #0x62 // #98 0.00 : 663e0: svc #0x0 0.00 : 663e4: ldp x20, x21, [x29, #24] 0.00 : 663e8: ldp x22, x23, [x29, #40] 0.00 : 663ec: b 66370 <__getdelim@@GLIBC_2.17+0x1f0> 0.00 : 663f0: ldr w2, [x0, #4] 0.00 : 663f4: add w2, w2, #0x1 0.00 : 663f8: str w2, [x0, #4] 0.00 : 663fc: tbz w1, #5, 66214 <__getdelim@@GLIBC_2.17+0x94> 0.00 : 66400: mov x24, #0xffffffffffffffff // #-1 0.00 : 66404: ldr x19, [x29, #16] 0.00 : 66408: b 66330 <__getdelim@@GLIBC_2.17+0x1b0> 0.00 : 6640c: nop 0.00 : 66410: ldr x0, [x21] 0.00 : 66414: strb wzr, [x0, x24] 0.00 : 66418: ldr w1, [x20] 0.00 : 6641c: ldr x19, [x29, #16] 0.00 : 66420: b 66328 <__getdelim@@GLIBC_2.17+0x1a8> 0.00 : 66424: nop 0.00 : 66428: mov x24, #0xffffffffffffffff // #-1 0.00 : 6642c: ldr w1, [x20] 0.00 : 66430: b 66328 <__getdelim@@GLIBC_2.17+0x1a8> 0.00 : 66434: nop 0.00 : 66438: mov x24, #0xffffffffffffffff // #-1 0.00 : 6643c: ldr w1, [x20] 0.00 : 66440: ldr x19, [x29, #16] 0.00 : 66444: b 66328 <__getdelim@@GLIBC_2.17+0x1a8> 0.00 : 66448: bl e3ba0 <pthread_setcanceltype@@GLIBC_2.17+0x30> 0.00 : 6644c: b 661f8 <__getdelim@@GLIBC_2.17+0x78> 0.00 : 66450: adrp x0, 17f000 <sys_sigabbrev@@GLIBC_2.17+0x320> 0.00 : 66454: ldr x0, [x0, #3624] 0.00 : 66458: mrs x1, tpidr_el0 0.00 : 6645c: mov w2, #0x16 // #22 0.00 : 66460: mov x24, #0xffffffffffffffff // #-1 0.00 : 66464: str w2, [x1, x0] 0.00 : 66468: b 66370 <__getdelim@@GLIBC_2.17+0x1f0> 0.00 : 6646c: ldr w1, [x20] 0.00 : 66470: mov x4, x0 0.00 : 66474: tbnz w1, #15, 6648c <__getdelim@@GLIBC_2.17+0x30c> 0.00 : 66478: ldr x0, [x20, #136] 0.00 : 6647c: ldr w1, [x0, #4] 0.00 : 66480: sub w1, w1, #0x1 0.00 : 66484: str w1, [x0, #4] 0.00 : 66488: cbz w1, 66494 <__getdelim@@GLIBC_2.17+0x314> 0.00 : 6648c: mov x0, x4 0.00 : 66490: bl 20e40 <gnu_get_libc_version@@GLIBC_2.17+0x130> 0.00 : 66494: str xzr, [x0, #8] 0.00 : 66498: ldxr w2, [x0] 0.00 : 6649c: stlxr w3, w1, [x0] 0.00 : 664a0: cbnz w3, 66498 <__getdelim@@GLIBC_2.17+0x318> 0.00 : 664a4: cmp w2, #0x1 0.00 : 664a8: b.le 6648c <__getdelim@@GLIBC_2.17+0x30c> 0.00 : 664ac: mov x1, #0x81 // #129 0.00 : 664b0: mov x2, #0x1 // #1 0.00 : 664b4: mov x3, #0x0 // #0 0.00 : 664b8: mov x8, #0x62 // #98 0.00 : 664bc: svc #0x0 0.00 : 664c0: b 6648c <__getdelim@@GLIBC_2.17+0x30c> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Tested-by: Leo Yan <leo.yan@linaro.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210615091704.259202-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-06-15 09:17:04 +00:00
--itrace::
Options for decoding instruction tracing data. The options are:
include::itrace.txt[]
To disable decoding entirely, use --no-itrace.
-m::
--modules::
Load module symbols. WARNING: use only with -k and LIVE kernel.
-l::
--print-line::
Print matching source lines (may be slow).
-P::
--full-paths::
Don't shorten the displayed pathnames.
--stdio:: Use the stdio interface.
--stdio2:: Use the stdio2 interface, non-interactive, uses the TUI formatting.
--stdio-color=<mode>::
'always', 'never' or 'auto', allowing configuring color output
via the command line, in addition to via "color.ui" .perfconfig.
Use '--stdio-color always' to generate color even when redirecting
to a pipe or file. Using just '--stdio-color' is equivalent to
using 'always'.
--tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
present, as when piping to other commands, the stdio interface is
used. This interfaces starts by centering on the line with more
samples, TAB/UNTAB cycles through the lines with more samples.
--gtk:: Use the GTK interface.
-C::
--cpu=<cpu>:: Only report samples for the list of CPUs provided. Multiple CPUs can
be provided as a comma-separated list with no space: 0,1. Ranges of
CPUs are specified with -: 0-2. Default is to report samples on all
CPUs.
--asm-raw::
Show raw instruction encoding of assembly instructions.
--show-total-period:: Show a column with the sum of periods.
--source::
Interleave source code with assembly code. Enabled by default,
disable with --no-source.
--symfs=<directory>::
Look for files with symbols relative to this directory.
-M::
--disassembler-style=:: Set disassembler style for objdump.
--objdump=<path>::
Path to objdump binary.
--prefix=PREFIX::
--prefix-strip=N::
Remove first N entries from source file path names in executables
and add PREFIX. This allows to display source code compiled on systems
with different file system layout.
--skip-missing::
Skip symbols that cannot be annotated.
perf annotate: Add basic support to event group view Add --group option to enable event grouping. When enabled, all the group members information will be shown with the leader so skip non-leader events. It only supports --stdio output currently. Later patches will extend additional features. $ perf annotate --group --stdio ... Percent | Source code & Disassembly of libpthread-2.15.so -------------------------------------------------------------------------------- : : : : Disassembly of section .text: : : 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>: 8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx 0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi 0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax 0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax 3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil 0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use 0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax 0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use 0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi 0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi 3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx) 0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use 0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx) 2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi 0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx) 83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586> 0.00 0.00 0.00 : 387dc0aa81: nop 0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax 0.00 0.00 0.00 : 387dc0aa84: retq ... Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 05:53:25 +00:00
--group::
Show event group information together
--demangle::
Demangle symbol names to human readable form. It's enabled by default,
disable with --no-demangle.
--demangle-kernel::
Demangle kernel symbol names to human readable form (for C++ kernels).
--percent-type::
Set annotation percent type from following choices:
global-period, local-period, global-hits, local-hits
The local/global keywords set if the percentage is computed
in the scope of the function (local) or the whole data (global).
The period/hits keywords set the base the percentage is computed
on - the samples period or the number of samples (hits).
--percent-limit::
Do not show functions which have an overhead under that percent on
stdio or stdio2 (Default: 0). Note that this is about selection of
functions to display, not about lines within the function.
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1]